steelman
Skill15 starsChanged 28 days agoMITView on GitHub
对想法、计划或决策做双向钢人论证:重述真实问题,给出正反双方最强论据,识别分歧与关键变量,只问一个关键问题,等回答后再判断。用于用户要求“双向钢人论证”“正反双方最强论证”或调用 $steelman 时;普通问答和直接执行请求不默认进入此流程。
13 other projects use a version of this.
Adopted by
Most recently taken up by
- rahul-kulkarni105/skillstheir own version, first seen Nov 8, 2026
- Bobby-cell-commits/steelman-skilltheir own version, first seen Nov 1, 2026
- sunnysxg/claude_skillstheir own version, first seen Oct 20, 2026
- natexai2026/2030-skillstheir own version, first seen Oct 20, 2026
- malinskibeniamin/skillstheir own version, first seen Oct 17, 2026
- rockcookies/skillstheir own version, first seen Oct 13, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- techiejd/claude-skill-steelman★ 10same name
- Bobby-cell-commits/steelman-skill★ 9same name
- damionrashford/Adversaria★ 9same name
- dgriffith/combat-epistemology★ 7same name
- malinskibeniamin/skills★ 4same name
- MichaelLeeHobbs/skills★ 1same name
- rockcookies/skills★ 1same name
- dilulloriccardo-arch/rigor-skills★ 0same name
- Nankov-ai/anthropics-skills★ 0same name
- natexai2026/2030-skills★ 0same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository27 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- harness/CLAUDE.mdCLAUDE.md
- android-live-photoSkill
- answer-my-questionSkill
- clear-and-brief-outputSkill
- codex-harnessSkill
- codex-quotaSkill
- crafted-webSkill
- create-opsSkill
- essay-polishSkill
- existing-ui-designSkill
- grillingSkill
- happy-app-experienceSkill
- happy-visual-workflowSkill
- image-effectsSkill
- mobile-app-interaction-reviewerSkill
- pc-web-interaction-reviewerSkill
- photo-to-styled-motionSkill
- show-meSkill
- skill-usage-auditSkill
- spec-debateSkill
- static-publishSkill
- story-uiSkill
- teach-meSkill
- topic-debateSkill
- video-to-cardsSkill
- web-e2eSkill
The file
Files
双向钢人论证
帮助用户检验问题定义与当前想法,不默认用户已经想清楚,也不急于赞同、反驳或给方案。使用用户的语言,给出充分、可审视的论据与依据;详细程度随问题复杂度调整,避免空泛凑字。
首轮:分析后只问一个问题
结合已有上下文,按以下顺序回应:
- 重述真正要解决的问题。 用最完整、最有力的方式说明用户的目标、当前主张,以及已知约束和成功标准。区分用户明确说过的内容与自己的理解;推测的动机或隐含前提应标为待验证的理解,不替用户认定。
- 支持当前想法的最强论证。 站在知情、理性的支持者立场,说明最有说服力的理由、成立条件,以及为什么这一方案可能优于可行替代方案。不要只列泛泛的好处。
- 反对当前想法的最强论证。 站在同样知情、理性的反对者立场,针对同一个主张提出最有力的挑战,说明机会成本、关键假设或替代路径。不要挑弱点凑数、歪曲主张或把反对者写成不理解问题的人。
- 找出真正分歧与关键变量。 说明争议来自事实判断、因果预期、价值排序还是风险承受能力;指出哪些证据、条件或变量变化最可能改变结论,以及改变的方向。有依据时给出临界条件,不编造精确阈值。
- 只问一个最关键的问题。 选择答案最可能改变判断、且尚未被上下文回答的问题。它应帮助区分双方论证的适用条件,不是泛泛地问“你怎么看”。不要把多个独立问题塞进一个句子或要求填写一组字段。
问完立即结束本轮,等待用户回答。首轮不提前给最终判断或行动方案,不替用户作答,也不通过连续消息追加问题。可提供少量中立选项方便回答,但不预选立场。
若缺少讨论对象,无法识别用户要检验的主张,只问一个问题来明确对象,等回答后再完成上述分析;不要凭空构造双方立场。
用户回答后:明确判断并推进
将回答接入上一轮已识别的分歧和关键变量,不机械重跑整套分析,也不默认进入无限追问。给出:
- 明确判断: 支持、反对、修改后推进,或在明确条件下成立;说明判断适用的边界。
- 理由: 解释这次回答如何改变或确认关键假设,为什么一方论证更有分量,并回应另一方仍然成立的最强异议。
- 下一步行动: 给出与判断一致、具体且可验证的下一步,说明如何判断结果。
如果仍缺少决定性信息,明确说明目前能成立的条件性判断,并将验证该信息作为下一步,不伪装确定,也不只说“看情况”。用户纠正问题定义时,先更新主张,再调整判断。
论证边界
- 公平呈现双方不等于双方证据相等。指出证据强弱和未知项,不为形式对称制造虚假平衡。
- 区分事实、假设与价值偏好;不编造研究、数据、引文或对用户的了解。需要外部核实时遵循当前环境的工具与来源要求。
- 本流程产出分析与行动建议;实际执行仍遵循用户已有授权。用户明确要求跳过、结束或改变流程时尊重其新指令。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

